Resumen

Epilepsy, as defined by the World Health Organization (WHO), is a chronic neurological disorder characterized by recurrent seizures. It is a non-transmissible condition that represents a significant proportion of the world's disease burden, affecting approximately 50 million people. Thus, investigating how to improve the different stages of diagnosis and prognosis is of great relevance. The aim of our study is to identify the varying needs in diagnosing and treating this condition. This thesis was conducted as part of a collaborative project between Los Andes university, the epileptology department of Fundacion Hospital Pediatrico de la Misericordia (HOMI) and Biotecgen S.A.S. The general project aims to design and develop a software solution for diagnosing refractory epilepsy. This includes predictive models that integrate information from different exams and analyze them individually. This thesis contributed to this project by establishing the requirements specification and software design. In addition, a classification model for epileptic seizures in EEG exams was developed, achieving high performance. Lastly, a bioinformatics pipeline was defined to extract the maximum possible miRNA information from raw sequencing reads.